D eep P lanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
Wei Fan · Wenlin Yao · Zheng Li · Feng Yao · Xin Liu · Liang Qiu · Qingyu Yin · Yangqiu Song · Bing Yin
摘要
Large language models (LLMs) augmented with multi-step reasoning and action generation abilities have shown promise in leveraging external tools to tackle complex tasks that require long-horizon planning. However, existing approaches either rely on implicit planning in the reasoning stage or intr...